Using machine learning to predict outcomes following suprainguinal bypass

Comparative performance of clinician and computational approaches in forecasting adverse outcomes in intermittent claudication

INTRODUCTION

Recent evidence has shown that machine learning(ML) techniques can accurately forecast adverse cardiovascular and limb events in patients with intermittent claudication. This is the first study to compare the predictive performance of ML versus traditional logistic regression(LR) and clinicians.

METHODS

An anonymised dataset of 99 patients with 27 baseline characteristics, compliance with best medical therapy/smoking cessation was used for comparison. Predictive performance was assessed using Area Under the Receiver Operating Characteristic curve(AUROC), F1 score and Brier score. ML, LR and clinicians were compared in their ability to predict outcomes including progression to chronic limb-threatening ischemia(CLTI) at 2 and 5 years, and probability of major adverse cardiovascular events(MACE) or limb events(MALE) upto 5 years. Independent variable importance ranking was performed to identify the most influential predictors.

RESULTS

The Least Absolute Shrinkage and Selection Operator(LASSO) based ML model was compared with(LR) and predictions from 8 clinicians. ML significantly outperformed LR and clinicians across all outcomes. AUROC for CLTI at 2 years:ML 0.885,LR 0.74,best clinician 0.63;CLTI at 5 years:ML 0.936,LR 0.808,best clinician 0.639;MACE at 5 years:ML 0.963,LR 0.759,best clinician 0.611;MALE: ML 0.957,LR 0.9,best clinician 0.677.Brier scores for the ML model demonstrated excellent accuracy: ML(0.03-0.07), compared to LR(0.10-0.22) and clinicians(>0.31).The machine learning model demonstrated superior predictive performance with F1 scores ranging from 0.80 to 0.86 across all outcomes, consistently outperforming both logistic regression(F1 scores: 0.61-0.72) and individual clinicians(F1 scores: 0.50-0.59).

CONCLUSION

ML-based prediction models significantly outperform traditional regression and clinician judgment, primarily due to their ability to capture complex non-linear associations between variables.

Predicting lack of clinical improvement following varicose vein ablation using machine learning

OBJECTIVE

Varicose vein ablation is generally indicated in patients with active/healed venous ulcers. However, patient selection for intervention in individuals without venous ulcers is less clear. Tools that predict lack of clinical improvement (LCI) after vein ablation may help guide clinical decision-making but remain limited. We developed machine learning (ML) algorithms that predict 1-year LCI after varicose vein ablation.

METHODS

The Vascular Quality Initiative database was used to identify patients who underwent endovenous or surgical varicose vein treatment for Clinical-Etiological-Anatomical-Pathophysiological (CEAP) C2 to C4 disease between 2014 and 2024. We identified 226 predictive features (111 preoperative [demographic/clinical], 100 intraoperative [procedural], and 15 postoperative [immediate postoperative course/complications]). The primary outcome was 1-year LCI, defined as a preoperative Venous Clinical Severity Score (VCSS) minus postoperative VCSS of ≤0, indicating no clinical improvement after vein ablation. The data were divided into training (70%) and test (30%) sets. Six ML models were trained using preoperative features with 10-fold cross-validation (Extreme Gradient Boosting [XGBoost], random forest, Naïve Bayes classifier, support vector machine, artificial neural network, and logistic regression). The primary model evaluation metric was area under the receiver operating characteristic curve (AUROC). The algorithm with the best performance was further trained using intraoperative and postoperative features. The focus was on preoperative features, whereas intraoperative and postoperative features were of secondary importance, because preoperative predictions offer the most potential to mitigate risk, such as deciding whether to proceed with intervention. Model calibration was assessed using calibration plots, and the accuracy of probabilistic predictions was evaluated with Brier scores. Performance was evaluated across subgroups based on age, sex, race, ethnicity, rurality, median Area Deprivation Index, prior ipsilateral varicose vein ablation, location of primary vein treated, and treatment type.

RESULTS

Overall, 33,924 patients underwent varicose vein treatment (30,602 endovenous [90.2%] and 3322 surgical [9.8%]) during the study period and 5619 (16.6%) experienced 1-year LCI. Patients who developed the primary outcome were older, more likely to be socioeconomically disadvantaged, and less likely to use compression therapy routinely. They also had less severe disease as characterized by lower preoperative VCSS, Varicose Vein Symptom Questionnaire scores, and CEAP classifications. The best preoperative prediction model was XGBoost, achieving an AUROC of 0.94 (95% confidence interval [CI], 0.93-0.95). In comparison, logistic regression had an AUROC of 0.71 (95% CI, 0.70-0.73). The XGBoost model had marginally improved performance at the intraoperative and postoperative stages, both achieving an AUROC of 0.97 (95% CI, 0.96-0.98). Calibration plots showed good agreement between predicted and observed event probabilities with Brier scores of 0.12 (preoperative), 0.11 (intraoperative), and 0.10 (postoperative). Of the top 10 predictors, 7 were preoperative features including VCSS, Varicose Vein Symptom Questionnaire score, CEAP classification, prior varicose vein ablation, thrombus in the greater saphenous vein, and reflux in the deep veins. Model performance remained robust across all subgroups.

CONCLUSIONS

We developed ML models that can accurately predict outcomes after endovenous and surgical varicose vein treatment for CEAP C2 to C4 disease, performing better than logistic regression. These algorithms have potential for important utility in guiding patient counseling and perioperative risk mitigation strategies to prevent LCI after varicose vein ablation.

Using machine learning to predict outcomes following transcarotid artery revascularization

Transcarotid artery revascularization (TCAR) is a relatively new and technically challenging procedure that carries a non-negligible risk of complications. Risk prediction tools may help guide clinical decision-making but remain limited. We developed machine learning (ML) algorithms that predict 1-year outcomes following TCAR. The Vascular Quality Initiative (VQI) database was used to identify patients who underwent TCAR between 2016 and 2023. We identified 115 features from the index hospitalization (82 pre-operative [demographic/clinical], 14 intra-operative [procedural], and 19 post-operative [in-hospital course/complications]). The primary outcome was 1-year post-procedural stroke or death. The data was divided into training (70%) and test (30%) sets. Six ML models were trained using pre-operative features with tenfold cross-validation. Overall, 38,325 patients were included (mean age 73.1 [SD 9.0] years, 14,248 [37.2%] female) and 2,672 (7.0%) developed 1-year stroke or death. The best pre-operative prediction model was XGBoost, achieving an AUROC of 0.91 (95% CI 0.90-0.92). In comparison, logistic regression had an AUROC of 0.68 (95% CI 0.66-0.70). The XGBoost model maintained excellent performance at the intra- and post-operative stages, with AUROC's (95% CI's) of 0.92 (0.91-0.93) and 0.94 (0.93-0.95), respectively. Our ML algorithm has potential for important utility in guiding peri-operative risk-mitigation strategies to prevent adverse outcomes following TCAR.

Machine Learning in Vascular Medicine: Optimizing Clinical Strategies for Peripheral Artery Disease

Purpose of Review

Peripheral Artery Disease (PAD), a condition affecting millions of patients, is often underdiagnosed due to a lack of symptoms in the early stages and management can be complex given differences in genetic and phenotypic characteristics. This review aims to provide readers with an update on the utility of machine learning (ML) in the management of PAD.

Recent Findings

Recent research leveraging electronic health record (EHR) data and ML algorithms have demonstrated significant advances in the potential use of automated systems, namely artificial intelligence (AI), to accurately identify patients who might benefit from further PAD screening. Additionally, deep learning algorithms can be used on imaging data to assist in PAD diagnosis and automate clinical risk stratification.ML models can predict major adverse cardiovascular events (MACE) and major adverse limb events (MALE) with considerable accuracy, with many studies also demonstrating the ability to more accurately risk stratify patients for deleterious outcomes after surgical intervention. These predictions can assist physicians in developing more patient-centric treatment plans and allow for earlier, more aggressive management of modifiable risk-factors in high-risk patients. The use of proteomic biomarkers in ML models offers a valuable addition to traditional screening and stratification paradigms, though clinical utility may be limited by cost and accessibility.

Summary

The application of AI to the care of PAD patients may enable earlier diagnosis and more accurate risk stratification, leveraging readily available EHR and imaging data, and there is a burgeoning interest in incorporating biological data for further refinement. Thus, the promise of precision PAD care grows closer. Future research should focus on validating these models via real-world integration into clinical practice and prospective evaluation of the impact of this new care paradigm.

Predicting inferior vena cava filter complications using machine learning

OBJECTIVE

Inferior vena cava (IVC) filter placement is associated with important long-term complications. Predictive models for filter-related complications may help guide clinical decision-making but remain limited. We developed machine learning (ML) algorithms that predict 1-year IVC filter complications using preoperative data.

METHODS

The Vascular Quality Initiative database was used to identify patients who underwent IVC filter placement between 2013 and 2024. We identified 77 preoperative demographic and clinical features from the index hospitalization when the filter was placed. The primary outcome was 1-year filter-related complications (composite of filter thrombosis, migration, angulation, fracture, and embolization or fragmentation, vein perforation, new caval or iliac vein thrombosis, new pulmonary embolism, access site thrombosis, or failed retrieval). The data were divided into training (70%) and test (30%) sets. Six ML models were trained using preoperative features with 10-fold cross-validation (Extreme Gradient Boosting, random forest, Naïve Bayes classifier, support vector machine, artificial neural network, and logistic regression). The primary model evaluation metric was area under the receiver operating characteristic curve (AUROC). Model robustness was assessed using calibration plot and Brier score. Performance was evaluated across subgroups based on age, sex, race, ethnicity, rurality, median Area Deprivation Index, planned duration of filter, landing site of filter, and presence of prior IVC filter placement.

RESULTS

Overall, 14,476 patients underwent IVC filter placement and 584 (4.0%) experienced 1-year filter-related complications. Patients with a primary outcome were younger (59.3 ± 16.7 years vs 63.8 ± 16.0 years; P < .001) and more likely to have thrombotic risk factors including thrombophilia, prior venous thromboembolism (VTE), and family history of VTE. The best prediction model was Extreme Gradient Boosting, achieving an AUROC of 0.93 (95% confidence interval, 0.92-0.94). In comparison, logistic regression had an AUROC of 0.63 (95% confidence interval, 0.61-0.65). Calibration plot showed good agreement between predicted/observed event probabilities with a Brier score of 0.07. The top 10 predictors of 1-year filter-related complications were (1) thrombophilia, (2) prior VTE, (3) antiphospholipid antibodies, (4) factor V Leiden mutation, (5) family history of VTE, (6) planned duration of IVC filter (temporary), (7) unable to maintain therapeutic anticoagulation, (8) malignancy, (9) recent or active bleeding, and (10) age. Model performance remained robust across all subgroups.

CONCLUSIONS

We developed ML models that can accurately predict 1-year IVC filter complications, performing better than logistic regression. These algorithms have potential to guide patient selection for filter placement, counselling, perioperative management, and follow-up to mitigate filter-related complications and improve outcomes.

Predicting Outcomes Following Lower Extremity Endovascular Revascularization Using Machine Learning

BACKGROUND

Lower extremity endovascular revascularization for peripheral artery disease carries nonnegligible perioperative risks; however, outcome prediction tools remain limited. Using machine learning, we developed automated algorithms that predict 30-day outcomes following lower extremity endovascular revascularization.

METHODS AND RESULTS

The National Surgical Quality Improvement Program targeted vascular database was used to identify patients who underwent lower extremity endovascular revascularization (angioplasty, stent, or atherectomy) for peripheral artery disease between 2011 and 2021. Input features included 38 preoperative demographic/clinical variables. The primary outcome was 30-day postprocedural major adverse limb event (composite of major reintervention, untreated loss of patency, or major amputation) or death. Data were split into training (70%) and test (30%) sets. Using 10-fold cross-validation, 6 machine learning models were trained using preoperative features. The primary model evaluation metric was area under the receiver operating characteristic curve. Overall, 21 886 patients were included, and 30-day major adverse limb event/death occurred in 1964 (9.0%) individuals. The best performing model for predicting 30-day major adverse limb event/death was extreme gradient boosting, achieving an area under the receiver operating characteristic curve of 0.93 (95% CI, 0.92-0.94). In comparison, logistic regression had an area under the receiver operating characteristic curve of 0.72 (95% CI, 0.70-0.74). The calibration plot showed good agreement between predicted and observed event probabilities with a Brier score of 0.09. The top 3 predictive features in our algorithm were (1) chronic limb-threatening ischemia, (2) tibial intervention, and (3) congestive heart failure.

CONCLUSIONS

Our machine learning models accurately predict 30-day outcomes following lower extremity endovascular revascularization using preoperative data with good discrimination and calibration. Prospective validation is warranted to assess for generalizability and external validity.